{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0019071412905625113,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.814282581125023e-05,
      "eval_loss": 0.4858570396900177,
      "eval_runtime": 1992.9812,
      "eval_samples_per_second": 5.539,
      "eval_steps_per_second": 2.77,
      "step": 1
    },
    {
      "epoch": 0.00019071412905625112,
      "grad_norm": 4.667794704437256,
      "learning_rate": 5e-05,
      "loss": 1.8996,
      "step": 5
    },
    {
      "epoch": 0.00038142825811250225,
      "grad_norm": 3.2646992206573486,
      "learning_rate": 0.0001,
      "loss": 1.7303,
      "step": 10
    },
    {
      "epoch": 0.00038142825811250225,
      "eval_loss": 0.39511317014694214,
      "eval_runtime": 2022.9241,
      "eval_samples_per_second": 5.457,
      "eval_steps_per_second": 2.729,
      "step": 10
    },
    {
      "epoch": 0.0005721423871687534,
      "grad_norm": 2.802189826965332,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5214,
      "step": 15
    },
    {
      "epoch": 0.0007628565162250045,
      "grad_norm": 2.8177430629730225,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3587,
      "step": 20
    },
    {
      "epoch": 0.0007628565162250045,
      "eval_loss": 0.3506273627281189,
      "eval_runtime": 2022.5654,
      "eval_samples_per_second": 5.458,
      "eval_steps_per_second": 2.729,
      "step": 20
    },
    {
      "epoch": 0.0009535706452812557,
      "grad_norm": 2.7057578563690186,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.4208,
      "step": 25
    },
    {
      "epoch": 0.0011442847743375068,
      "grad_norm": 2.461308717727661,
      "learning_rate": 5e-05,
      "loss": 1.2285,
      "step": 30
    },
    {
      "epoch": 0.0011442847743375068,
      "eval_loss": 0.33627158403396606,
      "eval_runtime": 2020.9262,
      "eval_samples_per_second": 5.462,
      "eval_steps_per_second": 2.731,
      "step": 30
    },
    {
      "epoch": 0.001334998903393758,
      "grad_norm": 2.625378131866455,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4156,
      "step": 35
    },
    {
      "epoch": 0.001525713032450009,
      "grad_norm": 2.802304983139038,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4285,
      "step": 40
    },
    {
      "epoch": 0.001525713032450009,
      "eval_loss": 0.33043166995048523,
      "eval_runtime": 2022.564,
      "eval_samples_per_second": 5.458,
      "eval_steps_per_second": 2.729,
      "step": 40
    },
    {
      "epoch": 0.0017164271615062602,
      "grad_norm": 2.6940152645111084,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.3441,
      "step": 45
    },
    {
      "epoch": 0.0019071412905625113,
      "grad_norm": 2.4607455730438232,
      "learning_rate": 0.0,
      "loss": 1.2691,
      "step": 50
    },
    {
      "epoch": 0.0019071412905625113,
      "eval_loss": 0.32941845059394836,
      "eval_runtime": 2023.4915,
      "eval_samples_per_second": 5.455,
      "eval_steps_per_second": 2.728,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.75266978594816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}